MAKE-Explainable AI (MAKE – eXAI)

CD-MAKE 2018 Workshop on explainable Artificial Intelligence

GOAL

This workshop aims to bring together international cross-domain experts interested in artificial intelligence/machine learning to stimulate research, engineering and evaluation in explainable AI – towards making machine decisions transparent, re-traceable, comprehensible, interpretable, explainable and reproducible. Accepted papers will be presented at the workshop orally or as poster and published in the IFIP CD-MAKE Volume of Springer Lecture Notes in Artificial Intelligence (LNAI). All submissions will be peer reviewed by at least three experts –
see authors instructions here: https://cd-make.net/authors-area/submission

BACKGROUND

Explainable AI is NOT a new field. Actually the problem of explainability is as old as AI and maybe the result of AI itself. While early expert systems consisted of handcrafted knowledge, which enabled reasoning over at least a narrowly well-defined domain, such systems had no learning capabilities and were poor in handling of uncertainties when (trying) to solve real-world problems. The big success of current AI solutions and ML algorithms is due to the practical applicability of statistical learning approaches in arbitrarily high dimensional spaces. Despite their huge successes their effectiveness is still limited by their inability to ”explain” their decisions in an understandable and retraceable way. Even if we understand the underlying mathematical theories, it is complicated and often impossible to get insight into the internal working of the models/algorithms and tools and to explain how and why a result was achieved. Future AI needs contextual adaptation, i.e. systems that help to construct explanatory models for solving real-world problems. Here it would be beneficial not to exclude human expertise, but to augment human intelligence with artificial intelligence.

TOPICS

In line with the general theme of the CD-MAKE conference of augmenting human intelligence with artificial intelligence, and Science is to test crazy ideas – Engineering is to bring these ideas into Business – we encourage to submit work on, but not limited to:

Frameworks, architectures, algorithms, tools for post-hoc/ante-hoc explainability
Theoretical approaches of explainability and transparent AI
Human intelligence vs. Artificial Intelligence (HCI — KDD)
Interactive machine learning with human(s)-in-the-loop (crowd intelligence)
Explanation User Interfaces and Human—Computer Interaction (HCI) for explainable AI
Fairness, accountability and trust
Ethical aspects, law and social responsibility
Business aspects of transparent AI

MOTIVATION

The grand goal of future explainable AI is to make results understandable and transparent and to answer questions of how and why a result was achieved. In fact: “Can we explain how and why a specific result was achieved by an algorithm?” In the future it will be essential not only to answer the question “Which of these animals is a cat?”, but to answer “Why is it a cat [Youtube Video]” – “What are the underlying explanatory facts that the machine learning algorithms made this decison”.

This highly relevant emerging area is important for all application areas, ranging from health informatics [1] to cyber defense [2], [3]. A partiuclar focus is on novel HCI and user interfaces for interactive machine learning [4].

[1] Andreas Holzinger, Chris Biemann, Constantinos S. Pattichis & Douglas B. Kell (2017). What do we need to build explainable AI systems for the medical domain? arXiv:1712.09923.
[2] David Gunning (2016) DARPA program on explainable artificial intelligence
[3] Katharina Holzinger, Klaus Mak, Peter Kieseberg & Andreas Holzinger (2018). Can we trust Machine Learning Results? Artificial Intelligence in Safety-Critical decision Support. ERCIM News, 112, (1), 42-43.
[4] Todd Kulesza, Margaret Burnett, Weng-Keen Wong & Simone Stumpf (2015). Principles of explanatory debugging to personalize interactive machine learning. Proceedings of the 20th International Conference on Intelligent User Interfaces (IUI 2015), 2015 Atlanta. ACM, 126-137, doi:10.1145/2678025.2701399.

Example: One motivation is the new European General Data Protection Regulation (GDPR and ISO/IEC 27001) entering into force on May, 25, 2018, and affects practically all machine learning and artificial intelligence applied to business. For example it will be difficult to apply black-box approaches for professional use in certain business applications, because they are not re-traceable and rarely able to explain on demand why a decision has been made.

Note: The GDPR replaces the data protection Directive 95/46/EC) of 1995. The regulation was adopted on 27 April 2016 and becomes enforceable from 25 May 2018 after now a two-year transition period and, unlike a directive, it does not require national governments to pass any enabling legislation, and is thus directly binding – which affects practically all data-driven businesses and particularly machine learning and AI technology.

WORKSHOP ORGANIZERS

Ajay CHANDER, Stanford University and Fujitsu Labs of America, Sunnyvale, US
Randy GOEBEL, University of Alberta, Edmonton, CA
Katharina HOLZINGER, Secure Business Austria, SBA-Research Vienna, AT
Freddy LECUE, Accenture Technology Labs, Dublin, IE and INRIA Sophia Antipolis, FR
Zeynep AKATA, University of Amsterdam, NL
Simone STUMPF, City, University London, UK
Peter KIESEBERG, Secure Business Austria, SBA-Research Vienna, AT
Andreas HOLZINGER, Medical University Graz, AT

SCIENTIFIC PROGRAMME COMMITTEE

see the conference main committee:
https://cd-make.net/committees
but we are also seeking addtional reviewers with special interest in this field –
if you want to volunteer as reviewer please contact Andreas Holzinger

David W. AHA, Naval Research Laboratory, Navy Center for Applied Research
in Artificial Intelligence, Washington, DC, US
Christian BAUCKHAGE, Fraunhofer Institute Intelligent Analysis and Informtation Systems IAIS, Sankt Augustin, and University of Bonn, DE
Bryce GOODMAN, Oxford Internet Institute and San Francisco Bay Area, CA, US
Marco Tulio RIBEIRO, Guestrin Group, University of Washington, Seattle, WA, US
Brian RUTTENBERG, Charles River Analytics, Cambridge, MA, US
Sameer SINGH, University of California UCI, Irvine, CA, US
Alison SMITH, University of Maryland, MD, US
Mohan SRIDHARAN, University of Auckland, NZ
Ramya MALUR SRINIVASAN, Fujitsu Labs of America, Sunnyvale, CA, US